Restoring Forgotten Knowledge in Non-Exemplar Class Incremental Learning through Test-Time Semantic Evolution
- URL: http://arxiv.org/abs/2503.16793v1
- Date: Fri, 21 Mar 2025 02:02:35 GMT
- Title: Restoring Forgotten Knowledge in Non-Exemplar Class Incremental Learning through Test-Time Semantic Evolution
- Authors: Haori Lu, Xusheng Cao, Linlan Huang, Enguang Wang, Fei Yang, Xialei Liu,
- Abstract summary: In Non-exemplar Class Incremental Learning (NECIL), forgetting arises because old classes are inaccessible.<n>We propose RoSE, which is a test-time semantic drift compensation framework.<n>We evaluate RoSE on CIFAR-100, TinyImageNet, and ImageNet100 datasets, under both cold-start and warm-start settings.
- Score: 11.50324946279326
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Continual learning aims to accumulate knowledge over a data stream while mitigating catastrophic forgetting. In Non-exemplar Class Incremental Learning (NECIL), forgetting arises during incremental optimization because old classes are inaccessible, hindering the retention of prior knowledge. To solve this, previous methods struggle in achieving the stability-plasticity balance in the training stages. However, we note that the testing stage is rarely considered among them, but is promising to be a solution to forgetting. Therefore, we propose RoSE, which is a simple yet effective method that \textbf{R}est\textbf{o}res forgotten knowledge through test-time \textbf{S}emantic \textbf{E}volution. Specifically designed for minimizing forgetting, RoSE is a test-time semantic drift compensation framework that enables more accurate drift estimation in a self-supervised manner. Moreover, to avoid incomplete optimization during online testing, we derive an analytical solution as an alternative to gradient descent. We evaluate RoSE on CIFAR-100, TinyImageNet, and ImageNet100 datasets, under both cold-start and warm-start settings. Our method consistently outperforms most state-of-the-art (SOTA) methods across various scenarios, validating the potential and feasibility of test-time evolution in NECIL.
Related papers
- No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery [53.08822154199948]
Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks.
This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics.
We develop a method that directly trains on scenarios with high learnability.
arXiv Detail & Related papers (2024-08-27T14:31:54Z) - An Effective Dynamic Gradient Calibration Method for Continual Learning [11.555822066922508]
Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks.
Due to the memory limit, we cannot store all the historical data, and therefore confront the catastrophic forgetting'' problem.
We develop an effective algorithm to calibrate the gradient in each updating step of the model.
arXiv Detail & Related papers (2024-07-30T16:30:09Z) - Adaptive Retention & Correction: Test-Time Training for Continual Learning [114.5656325514408]
A common problem in continual learning is the classification layer's bias towards the most recent task.<n>We name our approach Adaptive Retention & Correction (ARC)<n>ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
arXiv Detail & Related papers (2024-05-23T08:43:09Z) - Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information.
We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting.
Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
arXiv Detail & Related papers (2023-09-15T17:10:51Z) - EvCenterNet: Uncertainty Estimation for Object Detection using
Evidential Learning [26.535329379980094]
EvCenterNet is a novel uncertainty-aware 2D object detection framework.
We employ evidential learning to estimate both classification and regression uncertainties.
We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets.
arXiv Detail & Related papers (2023-03-06T11:07:11Z) - Lifelong Intent Detection via Multi-Strategy Rebalancing [18.424132535727217]
In this paper, we propose Lifelong Intent Detection (LID), which continually trains an ID model on new data to learn newly emerging intents.
Existing lifelong learning methods usually suffer from a serious imbalance between old and new data in the LID task.
We propose a novel lifelong learning method, Multi-Strategy Rebalancing (MSR), which consists of cosine normalization, hierarchical knowledge distillation, and inter-class margin loss.
arXiv Detail & Related papers (2021-08-10T04:35:13Z) - Always Be Dreaming: A New Approach for Data-Free Class-Incremental
Learning [73.24988226158497]
We consider the high-impact problem of Data-Free Class-Incremental Learning (DFCIL)
We propose a novel incremental distillation strategy for DFCIL, contributing a modified cross-entropy training and importance-weighted feature distillation.
Our method results in up to a 25.1% increase in final task accuracy (absolute difference) compared to SOTA DFCIL methods for common class-incremental benchmarks.
arXiv Detail & Related papers (2021-06-17T17:56:08Z) - Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms.
We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework.
Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
arXiv Detail & Related papers (2020-06-18T19:04:09Z) - AdaS: Adaptive Scheduling of Stochastic Gradients [50.80697760166045]
We introduce the notions of textit"knowledge gain" and textit"mapping condition" and propose a new algorithm called Adaptive Scheduling (AdaS)
Experimentation reveals that, using the derived metrics, AdaS exhibits: (a) faster convergence and superior generalization over existing adaptive learning methods; and (b) lack of dependence on a validation set to determine when to stop training.
arXiv Detail & Related papers (2020-06-11T16:36:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.